LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llama 3.2 3B Instruct by meta-llama

 »  All LLMs  »  meta-llama  »  Llama 3.2 3B Instruct   URL Share it on

  1500707   
  Arxiv:2204.05149   Arxiv:2405.16406   Autotrain compatible   Conversational   De   En   Endpoints compatible   Es   Facebook   Fr   Hi   Instruct   It   Llama   Llama-3   Meta   Pt   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Th
Model Card on HF 🤗: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct 

Llama 3.2 3B Instruct Benchmarks

MMLU Pro: 24.39
GPQA: 3.8
MUSR: 1.37
BBH: 24.06
IFEval: 73.93 vs 88 (so35)-16%
MATH Lvl 5: 17.15
LLME Score: 0.50419
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3.2 3B Instruct (meta-llama/Llama-3.2-3B-Instruct)

Llama 3.2 3B Instruct Parameters and Internals

Model Type 
text-generation
Use Cases 
Applications:
multilingual dialogue, knowledge retrieval, summarization, AI powered writing assistants, query and prompt rewriting
Limitations:
Use in any manner that violates applicable laws or regulations
Supported Languages 
English (officially supported), German (officially supported), French (officially supported), Italian (officially supported), Portuguese (officially supported), Hindi (officially supported), Spanish (officially supported), Thai (officially supported)
Training Details 
Data Sources:
publicly available online data
Data Volume:
up to 9 trillion tokens
Methodology:
Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO)
Context Length:
128000
Hardware Used:
H100-80GB GPUs (TDP of 700W)
Model Architecture:
Auto-regressive transformer with Grouped-Query Attention (GQA)
Input Output 
Accepted Modalities:
Multilingual Text
Output Format:
Multilingual Text and code
LLM NameLlama 3.2 3B Instruct
Repository 🤗https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct 
Model Size3b
Required VRAM6.5 GB
Updated2025-02-05
Maintainermeta-llama
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagesen de fr it pt hi es th
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Llama 3.2 3B Instruct

Model
Likes
Downloads
VRAM
...2 3B Instruct Unsloth Bnb 4bit3282152 GB
Llama 3.2 3B Instruct 4bit279020131 GB
Llama 3.2 3B Instruct GGUF108483020 GB
Llama 3.2 MEDIT 3B O1128346 GB
Llama 3.2 3B Instruct Bnb 4bit172619922 GB
Orca Mini V9 0 3B Instruct51316 GB
Gladiator Mini Exp 1211 3B056 GB
Komodo Llama 3.2 3B V2 Fp165756 GB
...r Mini Exp 1221 3B Instruct V2066 GB
...ator Mini Exp 1222 3B Instruct066 GB

Best Alternatives to Llama 3.2 3B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Orca Mini V9 5 3B Instruct128K / 6.5 GB2486
Llama 3.2 3B Instruct128K / 6.4 GB38007047
Llama 3.2 3B Bespoke Thought128K / 6.4 GB303
Llama 3.2 3B Instruct128K / 6.5 GB5791072
Llama 3.2 3B Math Oct128K / 6.5 GB907
Llama 3.2 3B RP DeepThink128K / 7.2 GB2732
Omni Reasoner3 Merged128K / 6.4 GB697
Eximius Persona 5B128K / 11.6 GB323
Orca Mini V9 6 3B Instruct128K / 6.5 GB424
Smol Llama 3.2 3B128K / 7.2 GB1380

Rank the Llama 3.2 3B Instruct Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42565 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer